Delete a tag
AI agents call mixpost_delete_tag to permanently remove resources in Mixpost — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes a tag from the Mixpost system. While tag deletion is typically reversible through re-creation, it is classified as Destructive because the action itself cannot be undone—the original tag and any associations are removed. The severity is medium rather than high because deleting a tag has limited blast radius (affects tag organization/filtering) compared to deleting posts or accounts.
From the tool's definition Tool name is 'mixpost_delete_tag' with description 'Delete a tag'. The verb 'delete' indicates irreversible removal of data.
Attacks that exploit this kind of access
Delete a tag. It is categorised as a Destructive tool in the Mixpost MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mixpost MCP server in PolicyLayer and add a rule for mixpost_delete_tag: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mixpost. Nothing to install.
mixpost_delete_tag is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the mixpost_delete_tag rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for mixpost_delete_tag. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
mixpost_delete_tag is provided by the Mixpost MCP server (pfarag/mixpost-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →